© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8147
    Prev
    Next
    INDEX
    Explanations

    & versus /or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¶ä»ĸ
    -0.09
    à¸ģาร
    -0.08
    Ñı
    -0.08
    ç¾İåĽ½åĴĮ
    -0.08
    à¸ĺรรมà¸Ĭาà¸ķิà¹ģละ
    -0.07
    å°ı
    -0.07
    éĿŀ
    -0.07
    人
    -0.07
    åĴĮ
    -0.07
     and
    -0.07
    POSITIVE LOGITS
    /or
    0.16
    /of
    0.13
    /OR
    0.11
    alus
    0.11
    ÑĶм
    0.10
     ëįĶë¶Īìĸ´
    0.10
    rew
    0.10
    å¾Ģ常ä¸Ģæł·
    0.10
    менÑĥ
    0.10
    amp
    0.10
    Activations Density 0.001%

    No Known Activations